plate-plan

Define or update Plate editor-behavior specs with a pass-gated, evidence-scored plan. Use for behavior law, authority maps, protocol rows, parity gates, research-backed winner shifts, editor chrome contracts, and implementation-roadmap changes.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/plate-plan/SKILL.md

Quality

Content

52%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is dense, well-sectioned policy with genuinely concrete artifacts, paths, and validation gates, but it is monolithic and heavily redundant. Hundreds of lines and several repeated rule blocks belong in one-level-deep reference files, and the repetition across sections creates version-drift risk (already visible in the conflicting pass-status vocabularies).

Suggestions

Split the self-contained rule blocks (Objection Ledger, Applicable Implementation Reviews matrix, Permanent-Home Test, Node Model taxonomy, High-Risk Deliberate Mode) into references/*.md files and keep SKILL.md as a short overview with clearly signaled links.

State each rule once in a single authoritative section (single-pass completion, completion gates, lens list) and reference it elsewhere; this would cut the file roughly in half and remove the pass-status vocabulary inconsistency.

Define one canonical pass/lane status vocabulary and use it identically in "Goal And Plan State" and the pass-state ledger row spec.

Dimension	Reasoning	Score
Conciseness	The 1001-line body restates the same material many times: the five review-lens names (shadcn, Vercel React, react-useeffect, performance-oracle, tdd) appear in at least six sections, and completion-gate rules are duplicated across "Confidence Score", "Goal And Plan State", "Pass Schedule", and "Pressure Passes". It does not explain concepts Claude already knows, so it stays above 1.	2 / 5
Actionability	For an instruction-only skill the guidance is concrete and executable: exact file paths, exact pass-status vocabularies, a weighted scorecard table, an 11-row applicability matrix, and enumerated required plan fields. Not 5 because many pressure passes say what to "prove" without any how.	4 / 5
Workflow Clarity	A numbered 9-pass schedule, a pass-state ledger format, and a conjunctive completion-gate checklist with an explicit feedback rule ("If any gate fails, status stays `pending`") give a clear validated sequence. Not 5 because the duplicated gate rules create minor incoherence — the allowed `current_pass_status` values include `revise` and `skipped` while pass-state ledger rows list only `pending`, `in_progress`, or `complete`.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the SKILL.md is a monolithic 1001-line document with clearly separable material inlined (objection-ledger spec, lens matrix, permanent-home test, node-model taxonomy). It is not a structureless wall of text — section headers, links, and tables give it organization — so it scores above 1.	2 / 5
	Total	12 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinctive description with an explicit trigger clause that clearly separates planning/spec-law work from execution. Its main weakness is jargon-only trigger vocabulary with no natural synonyms, and a when-clause phrased as artifact nouns rather than user situations.

Suggestions

Add natural user-facing trigger phrases to the Use-for clause (e.g., "Use when the user wants to change editor behavior law, asks for a Plate plan before implementation, or requests a spec/parity review") so it matches what users actually say.

Include a plain-language synonym or two alongside the jargon (e.g., "editor behavior spec/law") to broaden natural keyword coverage.

Mention the research-update and plan-ledger outputs that the body treats as first-class deliverables so the what-clause is comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain and deliverable ("Define or update Plate editor-behavior specs with a pass-gated, evidence-scored plan") and enumerates concrete artifact types ("authority maps, protocol rows, parity gates"). Falls short of 5 because only two actual verbs appear and core outputs from the body (research updates, plan ledger) are omitted.	4 / 5
Completeness	Both what ("Define or update Plate editor-behavior specs with a pass-gated, evidence-scored plan") and when ("Use for behavior law, authority maps, protocol rows...") are explicit. Not 5 because the when-clause enumerates artifact types rather than user-request trigger phrases.	4 / 5
Trigger Term Quality	Terms like "behavior law", "parity gates", and "protocol rows" match the project's internal vocabulary, but they are jargon-heavy with no synonyms or common natural-language variations a user might say (e.g., "spec change", "planning pass").	3 / 5
Distinctiveness Conflict Risk	"Plate editor-behavior specs" carves out a clear niche with a distinct trigger set (parity gates, protocol rows, winner shifts) that is unlikely to fire for unrelated planning or review skills.	5 / 5
	Total	16 / 20 Passed

Validation

68%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1002 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 29 missing, 29 deeper-than-1-level, 1 suspicious	Warning

	Total	11 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/plate-plan/SKILL.md
Commit: babb3c2

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.